CN117526336A - Equipment-level load control strategy selection system and method based on association rule analysis - Google Patents
Equipment-level load control strategy selection system and method based on association rule analysis Download PDFInfo
- Publication number
- CN117526336A CN117526336A CN202311355588.8A CN202311355588A CN117526336A CN 117526336 A CN117526336 A CN 117526336A CN 202311355588 A CN202311355588 A CN 202311355588A CN 117526336 A CN117526336 A CN 117526336A
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- real
- time
- discrete
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 42
- 238000011217 control strategy Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims description 31
- 238000012545 processing Methods 0.000 claims abstract description 47
- 230000033228 biological regulation Effects 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 230000001105 regulatory effect Effects 0.000 claims description 10
- 230000001276 controlling effect Effects 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 4
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 2
- 238000004378 air conditioning Methods 0.000 claims description 2
- 238000007621 cluster analysis Methods 0.000 claims description 2
- 238000013479 data entry Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 238000004146 energy storage Methods 0.000 claims description 2
- 229910052739 hydrogen Inorganic materials 0.000 claims description 2
- 239000001257 hydrogen Substances 0.000 claims description 2
- 238000003064 k means clustering Methods 0.000 claims description 2
- 230000007423 decrease Effects 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
- H02J3/144—Demand-response operation of the power transmission or distribution network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a system for selecting a device-level load control strategy based on association rule analysis, which comprises a data acquisition module, a data processing module, an association rule analysis and calculation module and a rule retrieval module, wherein the data acquisition module is used for acquiring historical data and real-time data of electric equipment, judging attributes of the historical data and the real-time data, carrying out association rule analysis on discrete historical data, and further screening out strong association rules related to the control strategy of the electric equipment through a set threshold value to form a system rule base; and then, according to the discrete real-time data, obtaining a control instruction for adjusting the load of the electric equipment. According to the equipment-level load control strategy selection system, historical data and real-time data of different electric equipment are collected, and a rule base is formed by learning a load regulation rule in the historical data, so that a load regulation instruction is intelligently selected according to the real-time data, and the load regulation efficiency of the electric equipment is improved.
Description
Technical Field
The invention belongs to the field of intelligent control of power loads, and particularly relates to a system and a method for selecting a device-level load control strategy based on association rule analysis.
Background
At present, an effective load control strategy is implemented on an electric equipment system, which is an important means for guaranteeing safe and stable operation of the system, and a traditional method for carrying out load regulation and control according to expert knowledge and physical modeling is not only needed to depend on knowledge storage and regulation and control experience of staff, but also has larger workload.
With the development of artificial intelligence technology, more and more importance is attached to the utilization of data, and more methods are provided for realizing intelligent load regulation and control based on the analysis of electric equipment data, the current method generally utilizes a machine learning method to construct a load prediction model, and the regulation and control are carried out according to the change trend of data after the parameters such as electric load and the like of future equipment are predicted by learning historical data rules. However, these methods have high requirements on model accuracy, so that a data analysis method is used to learn historical operation data and form a rule base selected by a load regulation strategy, and direct calling is necessary and efficient in practical application.
Disclosure of Invention
The invention aims to provide a system and a method for selecting a device-level load control strategy based on association rule analysis, so as to realize intelligent selection of load regulation and control instructions of electric equipment and improve power consumption load regulation and control efficiency.
In order to achieve the purpose, the equipment-level load control strategy selection system based on association rule analysis comprises a data acquisition module, a data processing module, an association rule analysis calculation module and a rule calling module;
the data acquisition module is used for acquiring historical data and real-time data of electric equipment and assisting in selecting a control strategy during load regulation; the data processing module is used for judging the attribute of the historical data and the real-time data, and if the historical data and the real-time data are judged to be discrete type data, the historical data and the real-time data are discrete type historical data and discrete type real-time data; if the historical data and the real-time data are judged to be continuous data, equal-width discretization processing and clustering discretization processing are carried out on the historical data and the real-time data, and labels in the appointed form of the historical data and the real-time data are given to obtain discrete historical data and discrete real-time data, so that a discrete historical data set and a discrete real-time data set are formed; the association rule analysis and calculation module is used for carrying out association rule analysis on the discrete type historical data obtained by the data processing module, calculating the support degree support, the confidence degree confidence and the lifting degree lift between the discrete type historical data and the load control strategy, and further screening out strong association rules related to the electric equipment control strategy through a set threshold value to form a system rule base; and the rule calling module finds the rule corresponding to the real-time data numerical range from the system rule base acquired by the association rule analysis and calculation module according to the discrete real-time data acquired by the data processing module, and compares the support, confidence and lifting results of all the screened rules, so as to acquire a control instruction for adjusting the load of electric equipment.
An equipment-level load control strategy selection system method based on association rule analysis comprises the following steps:
step 1, acquiring historical data and real-time data of electric equipment, and assisting in selecting a control strategy during load regulation;
step 2, judging the attributes of the historical data and the real-time data, and if the historical data and the real-time data are judged to be discrete data, judging the historical data and the real-time data to be discrete historical data and discrete real-time data; if the historical data and the real-time data are judged to be continuous data, equal-width discretization processing and clustering discretization processing are carried out on the historical data and the real-time data, and labels in the appointed form of the historical data and the real-time data are given to obtain discrete historical data and discrete real-time data, so that a discrete historical data set and a discrete real-time data set are formed;
step 3, carrying out association rule analysis on the discrete type historical data, calculating the support degree support, the confidence degree confidence and the lifting degree lift between the discrete type historical data and the load control strategy, and further screening out strong association rules related to the electric equipment control strategy through a set threshold value to form a system rule base;
and 4, finding out rules corresponding to the real-time data numerical range from the system rule base according to the discrete real-time data obtained in the step 2, and comparing the support, confidence and lifting results of all the screened rules to obtain a control instruction for adjusting the load of electric equipment.
The beneficial effects of the invention are as follows: according to the equipment-level load control strategy selection system, historical data and real-time data of different electric equipment are collected, and a rule base is formed by learning a load regulation rule in the historical data, so that a load regulation instruction is intelligently selected according to the real-time data, and the load regulation efficiency of the electric equipment is improved.
Drawings
FIG. 1 is a block diagram of a system of the present invention;
FIG. 2 is a flow chart of the method of the present invention;
the system comprises a 1-data acquisition module, a 2-data processing module, a 3-association rule analysis and calculation module and a 4-rule calling module.
Detailed Description
The invention is described in further detail below with reference to the attached drawings and specific examples:
an association rule analysis-based device-level load control strategy selection system, as shown in fig. 1, comprising: the system comprises a data acquisition module 1, a data processing module 2, an association rule analysis and calculation module 3 and a rule retrieval module 4;
the data acquisition module 1 is used for acquiring historical data and real-time data of electric equipment and assisting in selecting a control strategy during load regulation;
the data processing module 2 is configured to determine attributes of the historical data and the real-time data, and if it is determined that the historical data and the real-time data are discrete data, the historical data and the real-time data are discrete historical data and discrete real-time data, and a data pattern is an original data name; if the historical data and the real-time data are judged to be continuous data, equal-width discretization processing and clustering discretization processing are carried out on the historical data and the real-time data, labels in the appointed form of the historical data and the real-time data are given to obtain discrete historical data and discrete real-time data, a discrete historical data set and a discrete real-time data set are formed, and the data pattern is 'parameter name + category number'; discretizing the collected data to change all parameter data types into discretization so as to meet the requirements of an association rule learning algorithm.
The association rule analysis and calculation module 3 is used for performing association rule analysis on the discrete type historical data obtained by the data processing module 2, calculating the support degree support, the confidence degree confidence and the lifting degree lift between the discrete type historical data and the load control strategy, and further screening out strong association rules related to the electric equipment control strategy through a set threshold value to form a system rule base;
the rule retrieving module 4 finds the rule corresponding to the real-time data numerical range from the system rule base obtained by the association rule analysis and calculation module 3 according to the discrete real-time data obtained by the data processing module 2, and because the system more pays attention to the effect of the real-time load of the electric equipment in regulation and control, the rule containing the real-time load data range is screened out from the corresponding rules, and the support, confidence and lifting results of all the screened rules are compared, so that a control instruction for regulating the load of the electric equipment is obtained.
In the technical scheme, the sensor is arranged to collect historical data and real-time data when the load of the equipment is regulated and controlled:
the historical data comprise historical environment data, historical meteorological data, historical weather type data, historical date information, electric equipment type data, historical equipment load information, historical electric equipment operation data and specific instructions for regulating and controlling the historical electric equipment; the set formed by the historical data in a certain time forms a parameter historical operation data set;
the real-time data comprise real-time environment data, real-time meteorological data, real-time weather type data, real-time date information, electric equipment type data, real-time equipment load information, real-time electric equipment operation data and specific instructions for regulating and controlling the real-time electric equipment;
the historical environment data comprise historical environment temperature and humidity and historical pressure, and the real-time environment data comprise real-time environment temperature and humidity and real-time pressure;
the historical meteorological data comprises local historical temperature, local historical humidity and local historical pressure when load regulation is carried out on equipment; the real-time meteorological data comprise local real-time temperature, local real-time humidity and local real-time pressure when the load of the equipment is regulated and controlled;
the historical date information comprises historical holiday information and historical workday information, and the real-time date information comprises real-time holiday information and real-time workday information;
the historical weather type data comprises historical sunny day data, historical cloudy day data and historical rainy day data; the real-time weather type data comprise real-time sunny day data, real-time cloudy data and real-time rainy day data;
the electric equipment type data comprises electric automobile charging piles, a distributed photovoltaic system, a hydrogen energy storage system and a building air conditioning system.
In the above technical solution, the discrete data in the data processing module 2 includes historical weather type data, real-time weather type data, historical date information, real-time date information, electric equipment type information, specific instructions for controlling historical electric equipment, and specific instructions for controlling real-time electric equipment;
the continuous data in the data processing module 2 comprises historical environment data, real-time environment data, historical meteorological data, real-time meteorological data, historical equipment load information, real-time equipment load information, historical electric equipment operation parameter data and real-time electric equipment operation parameter data;
the data processing module 2 adopts continuous data processed in an equal-width discretization mode as historical environment data and real-time environment data, the continuous data processed in a clustering discretization mode of the data processing module 2 comprises historical equipment load information, real-time equipment load information, historical electric equipment operation parameter data and real-time electric equipment operation parameter data, and the clustering discretization mode adopts a k-means algorithm.
In the above technical solution, the specific implementation method of medium-width discretization processing in the data processing module 2 is as follows:
performing numerical analysis on the continuous data to obtain a numerical upper limit a and a numerical lower limit b of the continuous data, and determining the data interval length according to the distribution range of the continuous data to divide the continuous data into n types, wherein the lengths of each section of the data are the same as each other due to equal-width discrete processing:
l＝(a-b)/n
wherein n is the number of classifications, a is the upper limit of the value of the continuous data, b is the lower limit of the value of the continuous data, and the data are classified into n classes according to the upper limit of the value of the continuous data, and the numerical range of each class is [ b+ (k-1) l, (b+kl) ], wherein k is the kth segment of the continuous data, and the data are labeled according to the data name +k.
In the above technical solution, the specific implementation method of the k-means algorithm in the data processing module 2 is as follows:
step 21, based on the parameter historical operation data set, determining historical equipment load information and an optimal cluster number of historical electric equipment operation parameter data by using an elbow rule;
step 22, setting the clustering number of the data as K according to the optimal clustering number determined by an elbow rule, wherein the K-means clustering algorithm randomly selects K number values from the historical operation data set as initial clustering center points;
step 22.1, calculating the Euclidean distance between the data value of the historical operation data at a specific time point and the initial clustering center point, and attributing the data to a class in which the Euclidean distance between the data and the initial clustering center is closest:
wherein x is i For the data point of the i-th data point,representative kth cycle of tClustering center value->An ith cluster data set representing a t-th cycle, μ representing a set of K cluster centers, and n representing the total number of data entries;
the historical operating data can be classified into K classes;
step 22.2, re-calculating a new cluster center value, wherein a specific calculation formula is as follows:
wherein x is i For the data point of the i-th data point,cluster center value indicating the t+1st cycle,/->An ith cluster data set representing a t-th cycle, μ representing a set of K cluster centers, n representing the total number of entries of data in the kth class of data;
new K clustering centers can be obtained;
step 22.3, performing a second cycle, repeating step 22.1 and step 22.2 until the clustering center results are unchanged after the previous and subsequent cycles, so that the historical operation data can be divided into K types, the numerical range of each type of data can be obtained, and the parameter data is marked according to the format of 'parameter name + type number', so as to obtain discrete data.
In the above technical solution, the specific implementation method of step 21 is as follows:
setting different clustering numbers, carrying out cluster analysis on the historical operation data set, and calculating the error square sum of clustering results, wherein the formula is as follows:
wherein SSE is the sum of squares of errors, K is the total classification number of the data, namely the clustering algorithm classifies the data into K classes, n is the number of data in the ith class data set, and p ij For the value of the j-th element in the i-th class of data set, m i The clustering center is the i-th type data;
and the SSE value in the calculation result is reduced along with the increase of the cluster number until the SSE value is 0, and in the change process, a curve inflection point exists, and the cluster number corresponding to the point of suddenly reducing the SSE descending trend is the optimal cluster number of the historical operation data set.
In the above technical solution, the association rule analysis and calculation module 3 sorts the discrete historical data set obtained by the data processing module 2, and uses Apriori algorithm to perform association rule analysis on the data set, so as to obtain frequent item sets in the data and association rules between the item sets, and the specific implementation method is as follows:
step 31, calculating the support, confidence and promotion degree of item sets formed by different discrete data through an Apriori algorithm, and finding out frequent item sets frequently appearing in the discrete historical data; the Apriori algorithm is one of association rule analysis algorithms, and compared with other algorithms, the principle of calculating indexes such as the support degree and the like by the Apriori algorithm is easier to understand and is more suitable for analyzing the data after discrete processing;
step 32, setting a support degree threshold, a confidence degree threshold and a lifting degree threshold, and eliminating a result with weaker association rule to obtain a strong association rule;
step 33, screening association rules containing equipment load control instructions, obtaining the correlation between each parameter of historical data in the association rules and the load control strategies, forming a rule base, and further giving suggestions for equipment load control strategy selection under specific influence factors. Screening strong association rules related to the equipment load regulation instruction based on the calculation result to form a rule base of association between the equipment regulation scheme and the rest factors,
in the above technical solution, the specific implementation method of step 31 is as follows:
setting the item set as an item set A and an item set B, calculating the confidence, support and lifting degree of the item set A and the item set B, and finding out the strength relation of the association rule between the item set A and the item set B, wherein the calculation formula is as follows:
support{A、B}＝P(A∩B)
wherein, suppot { A, B } is the support, represents the probability that A item set and B item set appear at the same time, confidence { A- & gt B } is the confidence, represents the probability that B item set appears at the same time when A item set appears, lift { A- & gt B } is the promotion, represents the ratio of B item set appearance to B item set appearance when A item set appears, reflects the correlation of A and B in the association rule, is used for comparing the positive correlation or negative correlation degree between item sets, A and B represent the probability that A item set and B item set appear at the same time, P (A) is the probability that A item set appears, and P (B) is the probability that B item set appears;
and setting a support degree threshold, preferably 0.2, wherein the frequent item set is an item set with support degree exceeding the support degree threshold.
In the above technical solution, the method for obtaining the strong association rule in step 32 includes: setting a confidence threshold, wherein the confidence threshold is preferably 0.6; the strong association rule is a rule that the confidence level exceeds the confidence level threshold.
In the above technical solution, the specific implementation method of comparing the support, confidence and promotion results of all the screened rules by the rule invoking module 4 is as follows:
firstly, comparing the degree of lifting of each rule with the deviation degree of 1, and screening out the rule of 20 before sequencing; comparing the confidence values, and screening out rules of 10 before sequencing; and finally, comparing the sizes of the supporters to screen out the rule with the largest supporters.
A method of selecting a device level load control strategy, as shown in fig. 2, comprising the steps of:
step 1, acquiring historical data and real-time data of electric equipment, and assisting in selecting a control strategy during load regulation;
step 2, judging the attributes of the historical data and the real-time data, and if the historical data and the real-time data are judged to be discrete data, judging the historical data and the real-time data to be discrete historical data and discrete real-time data; if the historical data and the real-time data are judged to be continuous data, equal-width discretization processing and clustering discretization processing are carried out on the historical data and the real-time data, and labels in the appointed form of the historical data and the real-time data are given to obtain discrete historical data and discrete real-time data, so that a discrete historical data set and a discrete real-time data set are formed;
step 3, carrying out association rule analysis on the discrete type historical data, calculating the support degree support, the confidence degree confidence and the lifting degree lift between the discrete type historical data and the load control strategy, and further screening out strong association rules related to the electric equipment control strategy through a set threshold value to form a system rule base;
and 4, finding out rules corresponding to the real-time data numerical range from the system rule base according to the discrete real-time data obtained in the step 2, and comparing the support, confidence and lifting results of all the screened rules to obtain a control instruction for adjusting the load of electric equipment.
What is not described in detail in this specification is prior art known to those skilled in the art. It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be finally understood that the foregoing embodiments are merely illustrative of the technical solutions of the present invention and not limiting the scope of protection thereof, and although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that various changes, modifications or equivalents may be made to the specific embodiments of the invention, and these changes, modifications or equivalents are within the scope of protection of the claims appended hereto.
Claims (10)
1. An equipment-level load control strategy selection system based on association rule analysis is characterized in that: it comprises the following steps: the system comprises a data acquisition module (1), a data processing module (2), an association rule analysis and calculation module (3) and a rule calling module (4);
the data acquisition module (1) is used for acquiring historical data and real-time data of electric equipment and assisting in selecting a control strategy during load regulation;
the data processing module (2) is used for judging the attribute of the historical data and the real-time data, and if the historical data and the real-time data are judged to be discrete data, the historical data and the real-time data are discrete historical data and discrete real-time data; if the historical data and the real-time data are judged to be continuous data, equal-width discretization processing and clustering discretization processing are carried out on the historical data and the real-time data, and labels in the appointed form of the historical data and the real-time data are given to obtain discrete historical data and discrete real-time data, so that a discrete historical data set and a discrete real-time data set are formed;
the association rule analysis and calculation module (3) is used for carrying out association rule analysis on the discrete type historical data obtained by the data processing module (2), calculating the support degree support, the confidence degree confidence and the lifting degree lift between the discrete type historical data and the load control strategy, and further screening out strong association rules related to the electric equipment control strategy through a set threshold value to form a system rule base;
the rule invoking module (4) finds out the rule corresponding to the real-time data numerical range from the system rule base obtained by the association rule analysis and calculation module (3) according to the discrete real-time data obtained by the data processing module (2), and compares the support, confidence and lifting results of all the screened rules, so as to obtain a control instruction for adjusting the load of electric equipment.
2. An association rule analysis based device level load control policy selection system according to claim 1, wherein:
the historical data comprise historical environment data, historical meteorological data, historical weather type data, historical date information, electric equipment type data, historical equipment load information, historical electric equipment operation data and specific instructions for regulating and controlling the historical electric equipment;
the real-time data comprise real-time environment data, real-time meteorological data, real-time weather type data, real-time date information, electric equipment type data, real-time equipment load information, real-time electric equipment operation data and specific instructions for regulating and controlling the real-time electric equipment;
the historical environment data comprise historical environment temperature and humidity and historical pressure, and the real-time environment data comprise real-time environment temperature and humidity and real-time pressure;
the historical meteorological data comprises local historical temperature, local historical humidity and local historical pressure when load regulation is carried out on equipment; the real-time meteorological data comprise local real-time temperature, local real-time humidity and local real-time pressure when the load of the equipment is regulated and controlled;
the historical date information comprises historical holiday information and historical workday information, and the real-time date information comprises real-time holiday information and real-time workday information;
the historical weather type data comprises historical sunny day data, historical cloudy day data and historical rainy day data; the real-time weather type data comprise real-time sunny day data, real-time cloudy data and real-time rainy day data;
the electric equipment type data comprises electric automobile charging piles, a distributed photovoltaic system, a hydrogen energy storage system and a building air conditioning system.
3. An association rule analysis based device level load control policy selection system according to claim 1, wherein:
the discrete data in the data processing module (2) comprises historical weather type data, real-time weather type data, historical date information, real-time date information, electric equipment type information, specific instructions for regulating and controlling historical electric equipment and specific instructions for regulating and controlling real-time electric equipment;
the continuous data in the data processing module (2) comprises historical environment data, real-time environment data, historical meteorological data, real-time meteorological data, historical equipment load information, real-time equipment load information, historical electric equipment operation parameter data and real-time electric equipment operation parameter data;
the data processing module (2) adopts continuous data processed in an equal-width discretization mode as historical environment data and real-time environment data, the continuous data processed in a clustering discretization mode of the data processing module (2) comprises historical equipment load information, real-time equipment load information, historical electric equipment operation parameter data and real-time electric equipment operation parameter data, and the clustering discretization mode adopts a k-means algorithm.
4. A device-level load control strategy selection system based on association rule analysis as claimed in claim 3 wherein:
the specific implementation method of medium-width discretization processing of the data processing module (2) comprises the following steps:
performing numerical analysis on the continuous data to obtain a numerical upper limit a and a numerical lower limit b of the continuous data, and determining the data interval length according to the distribution range of the continuous data to divide the continuous data into n types, wherein the lengths of each segment of data are the same as each other:
l＝(a-b)/n
wherein n is the number of classifications, a is the upper limit of the value of the continuous data, b is the lower limit of the value of the continuous data, and the data are classified into n classes according to the upper limit of the value of the continuous data, and the value range of each class is [ b+ (k-1) l, (b+kl) ], wherein k is the kth segment of the continuous data.
5. A device-level load control strategy selection system based on association rule analysis as claimed in claim 3 wherein: the specific implementation method of the k-means algorithm in the data processing module (2) comprises the following steps:
step 21, based on the parameter historical operation data set, determining historical equipment load information and an optimal cluster number of historical electric equipment operation parameter data by using an elbow rule;
step 22, setting the clustering number of the data as K according to the optimal clustering number determined by an elbow rule, wherein the K-means clustering algorithm randomly selects K number values from the historical operation data set as initial clustering center points;
step 22.1, calculating the Euclidean distance between the data value of the historical operation data at a specific time point and the initial clustering center point, and attributing the data to the data in the class with the closest Euclidean distance with the initial clustering center:
wherein x is i For the data point of the i-th data point,the kth cluster center value of the t cycles represented,/->An ith cluster data set representing a t-th cycle, μ representing a set of K cluster centers, and n representing the total number of data entries;
the historical operating data can be classified into K classes;
step 22.2, re-calculating a new cluster center value, wherein a specific calculation formula is as follows:
wherein x is i For the data point of the i-th data point,cluster center value indicating the t+1st cycle,/->An ith cluster data set representing a t-th cycle, μ representing a set of K cluster centers, n representing the total number of entries of data in the kth class of data;
new K clustering centers can be obtained;
step 22.3, performing a second cycle, and repeating the steps 22.1 and 22.2 until the clustering center results are unchanged after the previous and subsequent cycles, so that the historical operation data can be divided into K types, and the numerical range of each type of data can be obtained to obtain discrete data.
6. An association rule analysis based device level load control policy selection system according to claim 5, wherein: the specific implementation method of the step 21 is as follows:
setting different clustering numbers, carrying out cluster analysis on the historical operation data set, and calculating the error square sum of clustering results, wherein the formula is as follows:
wherein SSE is the sum of squares of errors, K is the total classification number of data, n is the number of data in the ith class of data set, and p ij For the value of the j-th element in the i-th class of data set, m i The clustering center is the i-th type data;
and the clustering number corresponding to the point where the SSE descending trend suddenly decreases is the optimal clustering number of the historical operation data set.
7. An association rule analysis based device level load control policy selection system according to claim 1, wherein: the specific implementation method of the association rule analysis and calculation module (3) comprises the following steps:
step 31, calculating the support, confidence and promotion degree of item sets formed by different discrete data through an Apriori algorithm, and finding out frequent item sets frequently appearing in the discrete historical data;
step 32, setting a support degree threshold, a confidence degree threshold and a lifting degree threshold, and eliminating a result with weaker association rule to obtain a strong association rule;
and step 33, screening association rules containing equipment load regulation and control instructions, obtaining the correlation between each parameter of historical data in the association rules and the load regulation and control strategy, and forming a rule base.
8. An association rule analysis based device level load control policy selection system according to claim 7, wherein: the specific implementation method of the step 31 is as follows:
setting the item set as an item set A and an item set B, calculating the confidence, support and lifting degree of the item set A and the item set B, and finding out the strength relation of the association rule between the item set A and the item set B, wherein the calculation formula is as follows:
supportPA、B}＝P(A∩B)
wherein support { A, B } is a support, represents the probability of the simultaneous occurrence of the A item set and the B item set, confidence { A.fwdarw.B } is a confidence, represents the probability of the simultaneous occurrence of the B item set when the A item set occurs, lift { A.fwdarw.B } is a promotion, represents the ratio of the occurrence of the B item set to the occurrence of the B item set when the A item set occurs, A.U.B represents the probability of the simultaneous occurrence of the A item set and the B item set, P (A) is the probability of the occurrence of the A item set, and P (B) is the probability of the occurrence of the B item set;
the frequent item set is an item set with the support degree exceeding a support degree threshold value;
the method for obtaining the strong association rule in the step 32 is as follows: and setting a confidence coefficient threshold value, wherein the strong association rule is a rule with the confidence coefficient exceeding the confidence coefficient threshold value.
9. An association rule analysis based device level load control policy selection system according to claim 1, wherein:
the specific implementation method for comparing the support, confidence and lifting results of all the screened rules by the rule calling module (4) is as follows:
firstly, comparing the degree of lifting of each rule with the deviation degree of 1, and screening out the rule of 20 before sequencing; comparing the confidence values, and screening out rules of 10 before sequencing; and finally, comparing the sizes of the supporters to screen out the rule with the largest supporters.
10. A method of selecting a device-level load control strategy, comprising the steps of:
step 1, acquiring historical data and real-time data of electric equipment, and assisting in selecting a control strategy during load regulation;
step 2, judging the attributes of the historical data and the real-time data, and if the historical data and the real-time data are judged to be discrete data, judging the historical data and the real-time data to be discrete historical data and discrete real-time data; if the historical data and the real-time data are judged to be continuous data, equal-width discretization processing and clustering discretization processing are carried out on the historical data and the real-time data, and labels in the appointed form of the historical data and the real-time data are given to obtain discrete historical data and discrete real-time data, so that a discrete historical data set and a discrete real-time data set are formed;
step 3, carrying out association rule analysis on the discrete type historical data, calculating the support degree support, the confidence degree confidence and the lifting degree lift between the discrete type historical data and the load control strategy, and further screening out strong association rules related to the electric equipment control strategy through a set threshold value to form a system rule base;
and 4, finding out rules corresponding to the real-time data numerical range from the system rule base according to the discrete real-time data obtained in the step 2, and comparing the support, confidence and lifting results of all the screened rules to obtain a control instruction for adjusting the load of electric equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311355588.8A CN117526336A (en) | 2023-10-19 | 2023-10-19 | Equipment-level load control strategy selection system and method based on association rule analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311355588.8A CN117526336A (en) | 2023-10-19 | 2023-10-19 | Equipment-level load control strategy selection system and method based on association rule analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117526336A true CN117526336A (en) | 2024-02-06 |
Family
ID=89759622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311355588.8A Pending CN117526336A (en) | 2023-10-19 | 2023-10-19 | Equipment-level load control strategy selection system and method based on association rule analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117526336A (en) |
-
2023
- 2023-10-19 CN CN202311355588.8A patent/CN117526336A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107368926B (en) | A kind of more natural parameter sensing method for amalgamation processing of intelligent environment carrying robot identification floor | |
| CN107766990B (en) | Method for predicting power generation power of photovoltaic power station | |
| CN111008504B (en) | Wind power prediction error modeling method based on meteorological pattern recognition | |
| CN104050242A (en) | Feature selection and classification method based on maximum information coefficient and feature selection and classification device based on maximum information coefficient | |
| CN105701572B (en) | Photovoltaic short-term output prediction method based on improved Gaussian process regression | |
| CN108694502A (en) | A kind of robot building unit self-adapting dispatching method based on XGBoost algorithms | |
| CN106499656A (en) | A kind of fan wind speed intelligent control method | |
| CN108764588A (en) | A kind of temperature influence power prediction method based on deep learning | |
| CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
| CN115115127A (en) | Low-voltage transformer area intelligent regulation and control method and system based on deep learning | |
| CN111754029A (en) | Community load prediction system | |
| CN108985323A (en) | A kind of short term prediction method of photovoltaic power | |
| CN113268929B (en) | Short-term load interval prediction method and device | |
| CN112052985B (en) | Middle-short-term low-voltage prediction method based on lightgbm | |
| CN117315380A (en) | Deep learning-based pneumonia CT image classification method and system | |
| CN116091748B (en) | AIGC-based image recognition system and device | |
| CN113053536A (en) | Infectious disease prediction method, system and medium based on hidden Markov model | |
| CN117526336A (en) | Equipment-level load control strategy selection system and method based on association rule analysis | |
| CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
| CN116467631A (en) | Power fingerprint identification model training method, power fingerprint identification method and device | |
| CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
| CN114139783A (en) | Wind power short-term power prediction method and device based on nonlinear weighted combination | |
| CN112200346B (en) | Short-term wind power prediction method for weather fluctuation process division and matching | |
| CN114726751A (en) | Intelligent early warning method, system, equipment and storage medium for resource quality monitoring | |
| CN117370870B (en) | Knowledge and data compound driven equipment multi-working condition identification and performance prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |